Introduction to large language models (Lesson 01)

lessons/05_AI_intro/README.md

@@ -7,14 +7,14 @@ Welcome to the Week 5 in Python 200, Introduction to Artificial Intelligence!
 > For an introduction to the course, and a discussion of how to set up your environment, please see the [Welcome](../README.md) page.  
 
 ## Topics
-1. [Introduction to language processing](01_intro_nlp.md)  
-Explain what LLMs are and how they differ from earlier NLP models, and why language models have become so much more powerful recently. Discuss how language is converted to vectors (tokenization). Give broad overview of AI landscape.
+1. [Introduction to natural language processing](01_intro_nlp_llms.md)  
+An introduction to the field of natural language processing (NLP), and large language models (LLMs). Demystifying current large language models: an explanation of how they work, how they are trained. A demonstration of how meaning is represented in LLMs, with visualization. 
 
 2. [OpenAI Chat Completions API](02_open_ai_api.md)  
 Intro and overview of openai api chat completions endpoint. Go over required params (messages/model), but also the important optional params (max_tokens, temperature, top_p etc). Mention responses endpoint (more friendly to tools/agents). Discuss and demonstrate use of moderations endpoint.
 
 3. [Abstraction layers](03_abstractions.md)  
-Instead of getting locked into a single vendor or style, there are a few packages that provide an abstraction layer across LLM providers and local LLMs (you can run inference locally using Ollama). Here we'll discuss a few of these (langchain, liteLLM, any-llm). 
+Instead of getting locked into a single vendor or style, there are a few packages that provide an abstraction layer across LLM providers and local LLMs (you can run inference locally using Ollama). Here we'll discuss a few of these (langchain, liteLLM, any-llm), and show how to use liteLLM. 
 
 4. [Prompt engineering](04_prompt_engineering.md)  
 There are better and worse ways to get responses from a model, here we'll go over the fundamentals of *prompt engineering*. Zero shot, one shot, few-shot, and chain of thought prompting.